常用图表绘制 matplotlib/seaborn

Top 50 matplotlib Visualizations – The Master Plots (with full python code)

%matplotlib inline

import seaborn as sns
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import warnings

df = sns.load_dataset('iris')

Marginal Histogram 边缘直方图

Marginal histograms have a histogram along the X and Y axis variables. This is used to visualize the relationship between the X and Y along with the univariate distribution of the X and the Y individually. This plot if often used in exploratory data analysis (EDA).

# Custom the inside plot: options are: “scatter” | “reg” | “resid” | “kde” | “hex”
sns.jointplot(x=df["sepal_length"], y=df["sepal_width"], kind='kde')

<seaborn.axisgrid.JointGrid at 0x1e0caf2a4a8>

# Then you can pass arguments to each type:
sns.jointplot(x=df["sepal_length"], y=df["sepal_width"], kind='scatter', s=50, color='skyblue', edgecolor="m", linewidth=2)

<seaborn.axisgrid.JointGrid at 0x1e0caf18d68>

Correllogram 相关图

Correlogram is used to visually see the correlation metric between all possible pairs of numeric variables in a given dataframe (or 2D array).

df = pd.read_csv(r"D:\LearningFiles\DataSets\mtcars\mtcars.csv")
df.head()

	model	mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb
0	Mazda RX4	21.0	6	160.0	110	3.90	2.620	16.46	0	1	4	4
1	Mazda RX4 Wag	21.0	6	160.0	110	3.90	2.875	17.02	0	1	4	4
2	Datsun 710	22.8	4	108.0	93	3.85	2.320	18.61	1	1	4	1
3	Hornet 4 Drive	21.4	6	258.0	110	3.08	3.215	19.44	1	0	3	1
4	Hornet Sportabout	18.7	8	360.0	175	3.15	3.440	17.02	0	0	3	2

mtcars.csv 数据集

columns	meanings
mpg	Miles/(US) gallon
cyl	Number of cylinders
disp	Displacement (cu.in.)
hp	Gross horsepower
drat	Rear axle ratio
wt	Weight (1000 lbs)
qsec	1/4 mile time
vs	Engine (0 = V-shaped, 1 = straight)
am	Transmission (0 = automatic, 1 = manual)
gear	Number of forward gears
carb	Number of carburetors

corr = df.corr()
fig, ax = plt.subplots(figsize=(12, 10))
ax.matshow(corr)
plt.xticks(range(len(corr.columns)), corr.columns)
plt.yticks(range(len(corr.columns)), corr.columns)
plt.title('Correlogram of mtcars', fontsize=22)

Text(0.5,1.05,‘Correlogram of mtcars’)

plt.figure(figsize=(12,10), dpi= 80)
sns.heatmap(df.corr(), xticklabels=df.corr().columns, yticklabels=df.corr().columns, center=0, cmap='RdYlGn', annot=True)

# Decorations
plt.title('Correlogram of mtcars', fontsize=22)
plt.xticks(fontsize=12)
plt.yticks(fontsize=12)
plt.show()

Colormap tb10 is not recognized. Possible values are: Accent, Accent_r, Blues, Blues_r, BrBG, BrBG_r, BuGn, BuGn_r, BuPu, BuPu_r, CMRmap, CMRmap_r, Dark2, Dark2_r, GnBu, GnBu_r, Greens, Greens_r, Greys, Greys_r, OrRd, OrRd_r, Oranges, Oranges_r, PRGn, PRGn_r, Paired, Paired_r, Pastel1, Pastel1_r, Pastel2, Pastel2_r, PiYG, PiYG_r, PuBu, PuBuGn, PuBuGn_r, PuBu_r, PuOr, PuOr_r, PuRd, PuRd_r, Purples, Purples_r, RdBu, RdBu_r, RdGy, RdGy_r, RdPu, RdPu_r, RdYlBu, RdYlBu_r, RdYlGn, RdYlGn_r, Reds, Reds_r, Set1, Set1_r, Set2, Set2_r, Set3, Set3_r, Spectral, Spectral_r, Wistia, Wistia_r, YlGn, YlGnBu, YlGnBu_r, YlGn_r, YlOrBr, YlOrBr_r, YlOrRd, YlOrRd_r, afmhot, afmhot_r, autumn, autumn_r, binary, binary_r, bone, bone_r, brg, brg_r, bwr, bwr_r, cividis, cividis_r, cool, cool_r, coolwarm, coolwarm_r, copper, copper_r, cubehelix, cubehelix_r, flag, flag_r, gist_earth, gist_earth_r, gist_gray, gist_gray_r, gist_heat, gist_heat_r, gist_ncar, gist_ncar_r, gist_rainbow, gist_rainbow_r, gist_stern, gist_stern_r, gist_yarg, gist_yarg_r, gnuplot, gnuplot2, gnuplot2_r, gnuplot_r, gray, gray_r, hot, hot_r, hsv, hsv_r, icefire, icefire_r, inferno, inferno_r, jet, jet_r, magma, magma_r, mako, mako_r, nipy_spectral, nipy_spectral_r, ocean, ocean_r, pink, pink_r, plasma, plasma_r, prism, prism_r, rainbow, rainbow_r, rocket, rocket_r, seismic, seismic_r, spring, spring_r, summer, summer_r, tab10, tab10_r, tab20, tab20_r, tab20b, tab20b_r, tab20c, tab20c_r, terrain, terrain_r, viridis, viridis_r, vlag, vlag_r, winter, winter_r

Pair Plot 散点图矩阵

Pairwise plot is a favorite in exploratory analysis to understand the relationship between all possible pairs of numeric variables. It is a must have tool for bivariate analysis.

# Load Dataset
df = sns.load_dataset('iris')

# Plot
plt.figure(figsize=(10,8), dpi= 80)
sns.pairplot(df, kind="scatter", hue="species", plot_kws=dict(s=80, edgecolor="white", linewidth=2.5))
# Custom the inside plot: options are: “scatter” | “reg” | “resid” | “kde” | “hex”
plt.show()

# Load Dataset
df = sns.load_dataset('iris')

# Plot
plt.figure(figsize=(10,8), dpi= 80)
sns.pairplot(df, kind="reg", hue="species")
plt.show()

scatter_matrix 散点图矩阵

from sklearn.datasets import load_iris
iris_dataset = load_iris()
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(iris_dataset['data'], iris_dataset['target'], random_state=0)

iris_dataframe=pd.DataFrame(X_train, columns=iris_dataset.feature_names)
grr = pd.plotting.scatter_matrix(iris_dataframe, marker='o', c = y_train, hist_kwds={'bins':20}, figsize=(10, 8))

Ordered Bar Chart 有序柱状图

Ordered bar chart conveys the rank order of the items effectively. But adding the value of the metric above the chart, the user gets the precise information from the chart itself.

# Prepare Data
df_raw = pd.read_csv(r"D:\LearningFiles\DataSets\mpg_ggplot2.csv")
df_raw.head(10)

	manufacturer	model	displ	year	cyl	trans	drv	cty	hwy	fl	class
0	audi	a4	1.8	1999	4	auto(l5)	f	18	29	p	compact
1	audi	a4	1.8	1999	4	manual(m5)	f	21	29	p	compact
2	audi	a4	2.0	2008	4	manual(m6)	f	20	31	p	compact
3	audi	a4	2.0	2008	4	auto(av)	f	21	30	p	compact
4	audi	a4	2.8	1999	6	auto(l5)	f	16	26	p	compact
5	audi	a4	2.8	1999	6	manual(m5)	f	18	26	p	compact
6	audi	a4	3.1	2008	6	auto(av)	f	18	27	p	compact
7	audi	a4 quattro	1.8	1999	4	manual(m5)	4	18	26	p	compact
8	audi	a4 quattro	1.8	1999	4	auto(l5)	4	16	25	p	compact
9	audi	a4 quattro	2.0	2008	4	manual(m6)	4	20	28	p	compact

df = df_raw[['cty', 'manufacturer']].groupby('manufacturer').apply(lambda x: x.mean())
df.sort_values('cty', inplace=True)
df.reset_index(inplace=True)
df.head(10)

	manufacturer	cty
0	lincoln	11.333333
1	land rover	11.500000
2	dodge	13.135135
3	mercury	13.250000
4	jeep	13.500000
5	ford	14.000000
6	chevrolet	15.000000
7	pontiac	17.000000
8	audi	17.611111
9	nissan	18.076923

# Draw plot
import matplotlib.patches as patches

fig, ax = plt.subplots(figsize=(16,10), facecolor='white', dpi= 80)
ax.vlines(x=df.index, ymin=0, ymax=df.cty, color='firebrick', alpha=0.7, linewidth=20)

# Annotate Text
# 添加柱上的字
for i, cty in enumerate(df.cty):
    ax.text(i, cty+0.5, round(cty, 1), horizontalalignment='center')


# Title, Label, Ticks and Ylim
ax.set_title('Bar Chart for Highway Mileage', fontdict={'size':22})
ax.set(ylabel='Miles Per Gallon', ylim=(0, 30))
plt.xticks(df.index, df.manufacturer.str.upper(), rotation=60, horizontalalignment='right', fontsize=12)

# Add patches to color the X axis labels
# 没有实现上色
p1 = patches.Rectangle((.57, -0.005), width=.33, height=.13, alpha=.1, facecolor='green', transform=fig.transFigure)
p2 = patches.Rectangle((.124, -0.005), width=.446, height=.13, alpha=.1, facecolor='red', transform=fig.transFigure)
ax.add_artist(p1)
ax.add_artist(p2)

plt.show()

Density Plot 密度图

Density plots are a commonly used tool visualise the distribution of a continuous variable. By grouping them by the ‘response’ variable, you can inspect the relationship between the X and the Y. The below case if for representational purpose to describe how the distribution of city mileage varies with respect the number of cylinders.

# Import Data
df = pd.read_csv(r"D:\LearningFiles\DataSets\mpg_ggplot2.csv")
df.head(10)

	manufacturer	model	displ	year	cyl	trans	drv	cty	hwy	fl	class
0	audi	a4	1.8	1999	4	auto(l5)	f	18	29	p	compact
1	audi	a4	1.8	1999	4	manual(m5)	f	21	29	p	compact
2	audi	a4	2.0	2008	4	manual(m6)	f	20	31	p	compact
3	audi	a4	2.0	2008	4	auto(av)	f	21	30	p	compact
4	audi	a4	2.8	1999	6	auto(l5)	f	16	26	p	compact
5	audi	a4	2.8	1999	6	manual(m5)	f	18	26	p	compact
6	audi	a4	3.1	2008	6	auto(av)	f	18	27	p	compact
7	audi	a4 quattro	1.8	1999	4	manual(m5)	4	18	26	p	compact
8	audi	a4 quattro	1.8	1999	4	auto(l5)	4	16	25	p	compact
9	audi	a4 quattro	2.0	2008	4	manual(m6)	4	20	28	p	compact

# 此时只有一列数据:“cyl”
df = df.loc[df['cyl'] == 4, "cty"]
df.head(10)

运行结果：

0     18
1     21
2     20
3     21
7     18
8     16
9     20
10    19
32    19
33    22
Name: cty, dtype: int64

# Draw Plot
plt.figure(figsize=(16,10), dpi= 80)
sns.kdeplot(df.loc[df['cyl'] == 4, "cty"], shade=False, color="g", label="Cyl=4", alpha=.7)
sns.kdeplot(df.loc[df['cyl'] == 5, "cty"], shade=True, color="deeppink", label="Cyl=5", alpha=.7)
sns.kdeplot(df.loc[df['cyl'] == 6, "cty"], shade=True, color="dodgerblue", label="Cyl=6", alpha=.7)
sns.kdeplot(df.loc[df['cyl'] == 8, "cty"], shade=True, color="orange", label="Cyl=8", alpha=.7)

# Decoration
plt.title('Density Plot of City Mileage by n_Cylinders', fontsize=22)
plt.legend()
plt.show()

Box Plot 箱形图

它能显示出一组数据的最大值、最小值、中位数及上下四分位数。

Box plots are a great way to visualize the distribution, keeping the median, 25th 75th quartiles and the outliers in mind. However, you need to be careful about interpreting the size the boxes which can potentially distort the number of points contained within that group. So, manually providing the number of observations in each box can help overcome this drawback.

For example, the first two boxes on the left have boxes of the same size even though they have 5 and 47 obs respectively. So writing the number of observations in that group becomes necessary.

return:

boxes: the main body of the boxplot showing the quartiles and the median’s confidence intervals if enabled.
medians: horizontal lines at the median of each box.
whiskers: the vertical lines extending to the most extreme, non-outlier data points.
caps: the horizontal lines at the ends of the whiskers.
fliers: points representing data that extend beyond the whiskers (fliers).
means: points or lines representing the means.

# Import Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")

# Draw Plot
plt.figure(figsize=(13,10), dpi= 80)
#sns.boxplot(x='class', y='hwy', data=df, notch=False) 
sns.boxplot(x='class', y='cty', data=df, notch=False) 

# Decoration
plt.title('Box Plot of Highway Mileage by Vehicle Class', fontsize=22)
plt.ylim(10, 40)
plt.show()

Pie Chart 饼图

Pie chart is a classic way to show the composition of groups. However, its not generally advisable to use nowadays because the area of the pie portions can sometimes become misleading. So, if you are to use pie chart, its highly recommended to explicitly write down the percentage or numbers for each portion of the pie.
普通Pie图没有百分比，也没有legend

# Import
df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")

# Prepare Data
df = df_raw.groupby('class').size()

# Make the plot with pandas
df.plot(kind='pie', subplots=True, figsize=(8, 8))
plt.title("Pie Chart of Vehicle Class - Bad")
plt.ylabel("")
plt.show()

# Import
df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")

# Prepare Data
df = df_raw.groupby('class').size().reset_index(name='counts')

# Draw Plot
fig, ax = plt.subplots(figsize=(12, 7), subplot_kw=dict(aspect="equal"), dpi= 80)

data = df['counts']
categories = df['class']
explode = [0,0,0,0,0,0.1,0] # 扇形炸出来

def func(pct, allvals):
    absolute = int(pct/100.*np.sum(allvals))
    return "{:.1f}% ({:d} )".format(pct, absolute)

wedges, texts, autotexts = ax.pie(data, 
                                  autopct=lambda pct: func(pct, data),
                                  textprops=dict(color="w"), 
                                  colors=plt.cm.Dark2.colors,
                                 startangle=90,
                                 explode=explode)

# Decoration
ax.legend(wedges, categories, title="Vehicle Class", loc="center left", bbox_to_anchor=(1, 0, 0.5, 1))
plt.setp(autotexts, size=10, weight=700)
ax.set_title("Class of Vehicles: Pie Chart")
plt.show()

Time Series Plot 时序图

Time series plot is used to visualise how a given metric changes over time. Here you can see how the Air Passenger traffic changed between 1949 and 1969.

# Import Data
df = pd.read_csv('https://github.com/selva86/datasets/raw/master/AirPassengers.csv')

# Draw Plot
plt.figure(figsize=(16,10), dpi= 80)
plt.plot('date', 'traffic', data=df, color='tab:red')

# Decoration
plt.ylim(50, 750)
xtick_location = df.index.tolist()[::12]
# 间隔12个项切片

xtick_labels = [x[-4:] for x in df.date.tolist()[::12]]
plt.xticks(xtick_location, xtick_labels, rotation=0, fontsize=12, horizontalalignment='center', alpha=.7)
# 不加：ticks=, labels=

plt.yticks(fontsize=12, alpha=.7)
plt.title("Air Passengers Traffic (1949 - 1969)", fontsize=22)
plt.grid(axis='both', alpha=.3)

# Remove borders
plt.gca().spines["top"].set_alpha(0.5)    
plt.gca().spines["bottom"].set_alpha(0.3)
plt.gca().spines["right"].set_alpha(0.0)    
plt.gca().spines["left"].set_alpha(0.3)   
plt.show()